Drought and climate change impacts on cooling water shortages and electricity prices in Great Britain

Abstract

The risks of cooling water shortages to thermo-electric power plants are increasingly studied as an important climate risk to the energy sector. Whilst electricity transmission networks reduce the risks during disruptions, more costly plants must provide alternative supplies. Here, we investigate the electricity price impacts of cooling water shortages on Britain's power supplies using a probabilistic spatial risk model of regional climate, hydrological droughts and cooling water shortages, coupled with an economic model of electricity supply, demand and prices. We find that on extreme days (p99), almost 50% (7GW_e) of freshwater thermal capacity is unavailable. Annualized cumulative costs on electricity prices range from £29-66m.yr^-1 GBP2018, whilst in 20% of cases from £66-95m.yr^-1. With climate change, the median annualized impact exceeds £100m.yr^-1. The single year impacts of a 1-in-25 year event exceed >£200m, indicating the additional investments justifiable to mitigate the 1^st-order economic risks of cooling water shortage during droughts.

Fig. 1. Coupled hydroclimate and electricity supply–demand model framework for calculating welfare impacts of cooling water shortage for the electricity sector.

Large ensemble of regional climate simulations from Weather@Home are used to simulate daily electricity demand and force the DECIPHeR hydrological model. This determines water availability at power plants taking into account environmental flow requirements. Plant availability is used to adjust the electricity supply curve and re-calculate the drought-adjusted electricity strike price.

Fig. 2. Power plant unavailability (%) due to low flows at the power plant level under the three climate scenarios.

Boxplots show the distribution ofclimate uncertainty, which is in the order of ±3%. For the majority of power plants and compared to the Baseline scenario (a, d), unavailability doubles in the near future scenario (b, e) and almost triples in the far future scenario (c, f). Most severe impacts occur in the upstream tributaries and smaller rivers. Boxplot notch is the median, the bar is the inter-quartile range (IQR), whiskers extend to 5th and 95th percentiles, dots are outside this range.

Fig. 3. Impact duration curves and uncertainty of extreme impacts.

a Probability distribution of cumulative capacity impacted during an extreme 99th percentile day (i.e. impacts are exceeded only 1% of the time). b Uncertainty across model samples on a 99th percentile day. c Duration of impact with shaded uncertainty ranges (5th–95th percentiles) across the three climate scenarios compared reveal that accumulated capacity unavailability, through time, can be substantial. d Gaussian kernel density combining data from b and c showing the bi-variate distribution for extreme impact days (x-axis) and cumulative impact duration (y-axis), clearly increasing in severity on both axes.

Fig. 4. Price impacts of low flows across the range of climate uncertainty samples.

a–c The cumulative, annualised additional cost that low flows imparts on system electricity prices in £million per year. d–f The distribution of impacts per month. Boxplot notch is the median, the bar is the inter-quartile range (IQR), whiskers extend to 5th and 95th percentiles, dots are outside this range. Total 2900 daily samples per month. % proportion of the median monthly electricity value (second y-axis) is based on the annual median electricity production divided by 12.

Fig. 5. Single year and return period impact curves.

a–c Curves show the impacts of each year ranked, for BS, NF and FF. Grey lines are the 100 30-year W@H samples and the coloured lines are the percentiles. d Ranking of impacts by year for the 50th (thick), and 5th/95th (dashed) percentiles compared. e Return periods for the annual impact, for the three climate scenarios.

Fig. 6. Sensitivity of results to monthly variation in renewables production and long-term fuel price changes.

a Sensitivity of additional electricity costs during months with low (10th percentile), median and high (90th percentile) non-thermal renewables production. b Overall, these additional costs may be relatively small compared with the system costs and seasonal fluctuation. c Distribution of costs in alternative scenarios (right halves) compared to Baseline climate: low and high fuel costs; and near future (NF) and far future (FF) climate impacts; compared with the baseline (BS in grey/green). Boxplot notch is the median, the bar is the inter-quartile range (IQR), whiskers extend to 5th and 95th percentiles, dots are outside this range (a, b). Dashed lines show the median and inter-quartile ranges (c).

Fig. 7. Boxplots of the log Nash–Sutcliffe efficiency performance of the DECIPHeR hydrological model.

Results are shown at each gauge compared with observed flows, for the top 100 parameterisations out of 10,000 per gauge. Boxplot notch is the median, the bar is the inter-quartile range (IQR), whiskers extend to 5th and 95th percentiles, dots are outside this range.

Fig. 8. Load duration curves (LDC) to determine the demand model performance.

a Comparison of the observed LDC for 2012–2017 in red, with 100 simulated LDCs from the 100 W@H climate samples. Note that the observed uncertainty range is considerably larger due to other socioeconomic factors such as changing demand. b Comparison of the baseline, near future and far future LDCs using nine percentiles across the climate uncertainty.

Fig. 9. Electricity demand timeseries for the baseline climate, using 100 W@H samples (grey), and the median in black.

a The full 30-year timeseries. Lower panels zoom into the timeseries. b One-year profile for year 10, months January through December. c Two-week profile for year 10 in mid-September, Monday through Monday.